Foundations For Transfer In Reinforcement Learning: A Taxonomy Of Knowledge Modalities

Abstract

Contemporary artificial intelligence systems exhibit rapidly growing abilities accompanied by the growth of required resources, expansive datasets and corresponding investments into computing infrastructure. Although earlier successes predominantly focus on constrained settings, recent strides in fundamental research and applications aspire to create increasingly general systems. This evolving landscape presents a dual panorama of opportunities and challenges in refining the generalisation and transfer of knowledge - the extraction from existing sources and adaptation as a comprehensive foundation for tackling new problems. Within the domain of reinforcement learning (RL), the representation of knowledge manifests through various modalities, including dynamics and reward models, value functions, policies, and the original data. This taxonomy systematically targets these modalities and frames its discussion based on their inherent properties and alignment with different objectives and m

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywulfmeier2023foundations

Related papers

• Reinforcement Learning With Knowledge Representation And Reasoning: A Brief Survey (2023)0.00
• An Information-theoretic Perspective On Intrinsic Motivation In Reinforcement Learning: A Survey (2022)11.93
• Multi-granularity Knowledge Transfer For Continual Reinforcement Learning (2024)2.26
• Heterogeneous Knowledge For Augmented Modular Reinforcement Learning (2023)0.00
• Contextual Intelligence The Next Leap For Reinforcement Learning (2026)0.00
• Zero-shot Cross-modal Transfer Of Reinforcement Learning Policies Through A Global Workspace (2024)0.00
• Transfer Learning In Deep Reinforcement Learning: A Survey (2020)20.93
• Exploiting Hierarchy For Learning And Transfer In Kl-regularized RL (2019)0.00